bisect

A Git bisect workflow that uses binary search through a repository's commits to find which commit introduced a bug.

In plain words
What is it for?
Use it to investigate when a bug first appeared and verify each candidate commit with commands such as a test suite.
Why use it?
It narrows a long history to the change that caused the problem, using a test command or manual checks to classify commits as working or broken.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/drn/dots/bisect
Any agent
npx skills add drn/dots --skill bisect
Clone the repo
git clone --depth 1 https://github.com/drn/dots

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.01038
Opus 5 $0.00014 $0.00519
Sonnet 5 $0.00006 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 2d ago against content hash edebbf89d687, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bisect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/skills/bisect/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Bisect

Find the exact commit that introduced a bug using binary search with automatic test verification.

Arguments

  • $ARGUMENTS - Required: a test command to verify the bug (e.g., "go test ./pkg/..." or "npm test"), or a description of the bug to investigate manually

Context

  • Current branch: !git branch --show-current
  • Git status: !git status --short
  • Recent commits (50): !git log --oneline -50 2>/dev/null | head -50
  • Test framework: !find . -maxdepth 1 \( -name go.mod -o -name Gemfile -o -name package.json -o -name Cargo.toml -o -name pyproject.toml \) 2>/dev/null | head -5
  • Latest tag: !git describe --tags --abbrev=0 2>/dev/null | head -1

Instructions

Step 0: Validate state

  • IF git status --short shows uncommitted changes, offer to stash them with git stash push -m "bisect: stashing before bisect". If the user declines, stop and tell them to commit or stash first.
  • IF $ARGUMENTS is empty, ask the user: "What test command should I run to detect the bug? Or describe the bug and I will check each commit manually."

Step 1: Determine boundaries

The "bad" commit is HEAD (current state where the bug exists).

For the "good" commit, ask the user or infer:

  • IF the user provides a known-good commit or tag, use it.
  • IF a latest tag exists, suggest it as the good commit: "Is the bug present in ? If not, I will use it as the good boundary."
  • OTHERWISE, suggest a commit from the recent history (e.g., 20 commits back) and ask the user to confirm.

Step 2: Start bisect

git bisect start
git bisect bad HEAD
git bisect good <good-commit>

Report how many commits are in the range and the estimated number of steps (log2).

IF the range exceeds 1000 commits, warn the user: "This is a large range ( commits, ~ steps). Consider narrowing the boundaries."

Step 3: Run bisect

IF the user provided a test command:

  • Use git bisect run <test-command> for automatic bisection.
  • The test command should exit 0 for "good" (bug not present) and non-zero for "bad" (bug present).
  • Monitor the output. IF the test command exits with 125 (skip), report that the commit could not be tested and bisect will skip it.

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 111 lines · 28 tokens per session scan A edebbf89d687

Subscribe to this mod's changes

bisect is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,038 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens